Universal Approximation Theorem for Equivariant Maps by Group CNNs
arXiv:2012.13882
Abstract
Group symmetry is inherent in a wide variety of data distributions. Data processing that preserves symmetry is described as an equivariant map and often effective in achieving high performance. Convolutional neural networks (CNNs) have been known as models with equivariance and shown to approximate equivariant maps for some specific groups. However, universal approximation theorems for CNNs have been separately derived with individual techniques according to each group and setting. This paper provides a unified method to obtain universal approximation theorems for equivariant maps by CNNs in various settings. As its significant advantage, we can handle non-linear equivariant maps between infinite-dimensional spaces for non-compact groups.
References in corpus (7)
- On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
- Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
- On Learning Sets of Symmetric Elements
- Universal approximations of permutation invariant/equivariant functions by deep neural networks
- A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks
- Universal Equivariant Multilayer Perceptrons
- On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps